google/gemma-4-E2B-it-qat-q4_0-gguf
Quantization (fewer layers) vs google/gemma-4-E2B-it-qat-q4_0-unquantized. google/gemma-4-E2B-it-qat-q4_0-gguf matches part of google/gemma-4-E2B-it-qat-q4_0-unquantized (505 of its 1951 tensors; the rest of google/gemma-4-E2B-it-qat-q4_0-unquantized has no counterpart). On the shared part: google/gemma-4-E2B-it-qat-q4_0-gguf is a GGUF quantization (Q6_K/Q4_0) of the same weights: 228 tensors match exactly and 277 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/227, MLP 0/105, other 0/71, Attention 0/100
1 derivatives checked
- ego0op/gemma-4-E2B-it-qat-q4_0-latin-gguf: Same weights, repacked